activity
20172022
most citedA Survey on Explainability in Machine Reading Comprehension

32 citations · 109 across the 18 of their papers we have counts for

collaborators
Showing cs.CLShow all

26 papers · 1 filter

cs.CL20229 cited

Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language

Mael Jullien, Marco Valentino, Andre Freitas

With the methodological support of probing (or diagnostic classification), recent studies have demonstrated that Transformers encode syntactic and semantic information to some exte…

cs.CL2021

Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders

Giangiacomo Mercatali, André Freitas

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches…

cs.CL2021

Architectures of Meaning, A Systematic Corpus Analysis of NLP Systems

Oskar Wysocki, Malina Florea, Donal Landers +1

This paper proposes a novel statistical corpus analysis framework targeted towards the interpretation of Natural Language Processing (NLP) architectural patterns at scale. The prop…

cs.CL20216 cited

Context-Preserving Text Simplification

Christina Niklaus, Matthias Cetto, André Freitas +1

We present a context-preserving text simplification (TS) approach that recursively splits and rephrases complex English sentences into a semantic hierarchy of simplified sentences.…

cs.CL20213 cited

Encoding Explanatory Knowledge for Zero-shot Science Question Answering

Zili Zhou, Marco Valentino, Donal Landers +1

This paper describes N-XKT (Neural encoding based on eXplanatory Knowledge Transfer), a novel method for the automatic transfer of explanatory knowledge through neural encoding mec…

cs.CL2021

Supporting Context Monotonicity Abstractions in Neural NLI Models

Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan +2

Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monoton…